Reference

API Quick Reference

A compact index of the primary NeuraLib and NeuraLib_Models entry points. Use the conceptual guides for shape rules, lifecycle, and safe usage.

Updated Publisher Alien_AlgorithmsPine Script v6

Core API

Model setup

sequential()compileConfig()build()compile()rng()

Sequential

input()dense()qHead()activation()dropout()layerNorm()flatten()reshape()block()trainOnBatch()backward()step()predict()predictMC()evaluate()fitDataset()fitRollingDataset()getWeightsArray()setWeightsArray()softUpdateFrom()

CompileConfig

optimizer()schedule()loss()reduction()metric()batchSize()epochsPerBar()evalStride()historyLength()clipNorm()clipValue()gradAccumSteps()withTrainingGate()trainEveryCall()

Datasets

windowDataset()rollingDataset()pushRow()pushBuilderRow()pushNextReturnRow()pushNextDirectionRow()ready()size()lastBatch()toBatch()unrollBatch()trainBatch()validationBatch()setInputScaler()setTargetScaler()scaleInput()scaleTarget()inverseScaleTarget()clear()

Tensor creation

scalar()vector()matrix2d()zeros()ones()full()shapeFromDims()

Tensor methods

reshape()flatten()row()get1d()sum()mean()variance()normL2()argmax()dot()

Matrix methods

matmul()transpose()add()subtract()multiply()divide()scale()activate()softmax()sliceRows()sliceCols()concatRows()concatCols()globalAvgPool1d()globalMaxPool1d()

Scalers

zScoreScaler()minMaxScaler()runningZScoreScaler()noneScaler()fit()partialFit()transform()inverseTransform()

Optimizers & schedules

sgd()momentum()rmsprop()adam()adamW()constantSchedule()stepDecay()cosineDecay()warmupCosine()currentRate()

Losses & metrics

mse()mae()huber()logCosh()binaryCrossEntropy()binaryCrossEntropyFromLogits()categoricalCrossEntropy()softmaxCrossEntropyFromLogits()directionalLoss()quantileLoss()multiHorizonWeighted()sharpeLoss()metricValue()

Helpers

featureBuilder()earlyStopper()nextReturnValue()nextDirectionValue()

GraphBlock API

Structure

graphBlock()input()param()constScalar()constMatrix()output()

Math and neural operations

matmul()add()subtract()multiply()divide()scale()activate()softmax()transpose()layerNorm()dropout()

Structural and sequence operations

causalMask()sliceRows()concatRows()sliceCols()concatCols()reduceRows()reduceCols()globalAvgPool1d()globalMaxPool1d()attentionScore()attentionApply()conv1d()scanLstm()scanGru()

NeuraLib_Models API

Sequential methods

residualDense()duelingQHead()conv1d()temporalConvStack()globalAvgPool1d()globalMaxPool1d()lstm()gru()selfAttention()multiHeadSelfAttention()crossAttention()transformerEncoder()transformerEncoderStack()transformerDecoder()

Block factories

qHeadBlock()duelingQHeadBlock()residualDenseBlock()conv1dBlock()temporalConvStackBlock()globalAvgPool1dBlock()globalMaxPool1dBlock()lstmBlock()gruBlock()selfAttentionBlock()multiHeadSelfAttentionBlock()crossAttentionBlock()transformerEncoderBlock()transformerDecoderBlock()

Prioritized replay and sequence helpers

  • prioritizedReplayBuffer(featureCount, targetCount, maxRows, name)
  • pushExperience(features, targets, priority)
  • sampleBatch(batchSize, alpha, beta, seed)
  • updatePriority(index, priority)
  • toBatch(), ready(), size(), and clear()
  • pushPositionalEncoding(position, dimensions, maxPeriod, prefix)

Imports are version-pinned in Pine Script. Update the version number deliberately when a new published library version is required.

NeuraLib is a machine-learning research runtime for Pine Script. Model output is not financial advice and does not guarantee future performance. © Alien_Algorithms.